© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43932
    Prev
    Next
    INDEX
    Explanations

    Technical/academic topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.71
    ⓧ
    -0.70
     Agnes
    -0.59
    httphttps
    -0.56
    orni
    -0.54
    ship
    -0.52
    lici
    -0.50
    Шаг
    -0.50
    Хьажоргаш
    -0.50
     nase
    -0.49
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     wacht
    0.59
    DeleteBehavior
    0.59
    sidemargin
    0.57
    تقاوى
    0.56
     StatefulWidget
    0.54
    جوايز
    0.53
    anmoins
    0.53
     inoxydable
    0.52
    PROLOG
    0.51
    Activations Density 0.067%

    No Known Activations